We aimed to develop an automated, low-volume method for thrombocyte counting in capillary blood using the Sysmex predilution (PD) mode.
Microsamples were prepared by resuspension of 50 μL blood in 300 μL DCL CellPack. Thrombocyte counting was done in the impedance (PLT-I) and fluorescence (PLT-F) channels. The imprecision and bias was evaluated in >394 microsamples from adult blood. Preanalytical factors (skin-piercing, storage, and transportation in our pneumatic tube system) was assessed, and studies on pediatric microsamples were made for comparison. The improvement in analytical quality and turnaround time was examined.
For PLT-F, the imprecision was 1.1%–3.7%, and the bias was 10.1% (95% CI: 8.8–11.3). After skin-piercing, the bias was 8.1% (95% CI: 5.6–10.6) and the imprecision 1.9% (95% CI: 1.3–2.5). Thrombocyte counts kept stable after 4 h at room temperature (94.8% [95% CI: 93.2–96.4]) and after pneumatic tube transportation [6.7% (95% CI: 4.8–8.6)]. The bias of the PD mode for pediatric microsamples was 13.0% (95% CI: −8.4–34.4) in the PLT-F channel. The automated method had a considerably lower imprecision than the existing manual thrombocyte counting method and reduced turnaround times.
The automated microsample method offers a low-volume alternative for measurement of thrombocytes. The method appears useful also in pediatric samples.
The platelet fluorescent counting (PLT-F) method is utilized as a reflex test method following the initial test of the platelet impedance counting (PLT-I) method in clinical practice on the Sysmex XN-series automated hematology analyzer. Our aim is to establish reflex test rules for the PLT-F method by combining multiple parameters provided by the “CBC + DIFF” mode of the Sysmex XN-series automated hematology analyzer.
We tested 120 samples to evaluate the baseline bias between the PLT-F and PLT-I methods. Then, we selected 1256 samples to establish and test reflex test rules using seven machine learning models (decision Tree, random forest, neural network, logistic regression, k-nearest neighbor, support vector machine, and Naive Bayes). The training set and test set were divided at a ratio of 7:3. We evaluated the performance of machine learning models on the test set using various metrics to select the most valuable model.
The PLT-F method exhibited a high degree of correlation with the PLT-I method (r = 0.998). The random forest model emerged as the most valuable, boasting an accuracy of 0.893, an area under the curve of 0.954, an F1 score of 0.771, a recall of 0.719, a precision of 0.831, and a specificity of 0.950. The most important variable in the random forest model was mean cell volume, weighted at 15.09%.
The random forest model, which demonstrated high efficiency in our study, can be used to establish PLT reflex test rules based on the PLT-F method for the Sysmex XN-series automated hematology analyzer.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：